4 papers
EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming
Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Colton Payne +4
Large language models are increasingly used to reason about software vulnerabilities, but their outputs can silently violate domain knowledge, limiting their reliability in safety-…
From We to Me: Theory Informed Narrative Shift with Abductive Reasoning
Jaikrishna Manojkumar Patil, Divyagna Bavikadi, Kaustuv Mukherji +5
Effective communication often relies on aligning a message with an audience's narrative and worldview. Narrative shift involves transforming text to reflect a different narrative f…
Lattice Annotated Temporal (LAT) Logic for Non-Markovian Reasoning
Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Dyuman Aditya +5
We introduce Lattice Annotated Temporal (LAT) Logic, an extension of Generalized Annotated Logic Programs (GAPs) that incorporates temporal reasoning and supports open-world semant…
Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning
Kaustuv Mukherji, Devendra Parkar, Lahari Pokala +3
Recent advances in reinforcement learning (RL) have shown much promise across a variety of applications. However, issues such as scalability, explainability, and Markovian assumpti…